Towards a Greek Proverb Atlas: A Computational Spatial Exploration and Attribution of Greek Proverbs

Towards a Greek Proverb Atlas: A Computational Spatial Exploration and Attribution of Greek Proverbs | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Towards a Greek Proverb Atlas: A Computational Spatial Exploration and Attribution of Greek Proverbs John Pavlopoulos, Panos Louridas, Panagiotis Filos This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3360387/v4 This work is licensed under a CC BY 4.0 License Status: Posted Version 4 posted You are reading this latest preprint version Show more versions Abstract Proverbs carry wisdom transferred orally fromgeneration to generation. Based on the placethey were recorded, this study introducesa publicly-available and machine-actionabledataset of more than one hundred thousandGreek proverb variants. By quantifying thespatial distribution of proverbs, we show thatthe most widespread proverbs come from themainland while the least widespread proverbscome primarily from the islands. By focusingon the least dispersed proverbs, we present themost frequent tokens per location and under-take a benchmark in geographical attribution,using text classification and regression (textgeocoding). Our results show that this is a chal-lenging task for which specific locations can beattributed more successfully compared to oth-ers. The potential of our resource and bench-mark is showcased by two novel applications.First, we extracted terms moving the regressionprediction toward the four cardinal directions.Second, we leveraged conformal prediction toattribute 3,676 unregistered proverbs with sta-tistically rigorous predictions of locations eachof these proverbs was possibly registered in. Artificial Intelligence and Machine Learning natural language processing proverbs spatial exploration text geocoding geographical attribution Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 4 posted You are reading this latest preprint version Show more versions Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3360387","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":273070700,"identity":"b0829102-6ea0-4b89-8b31-dc76d6bb2363","order_by":0,"name":"John Pavlopoulos","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAp0lEQVRIiWNgGAWjYJCCAwwVQFKCNC1nSNXCwNhGihb+2b0HD/6cZ5fYL93A/LqCGC0Sd84lHObdlpw4c84BNsszRFlzI8fgMOM25sQNNxLYDBuI0SEP1HLw55z6xP1EazEAajnA23A4cYNEAvNDorQYghzGc+y48Yw7B9sYidIidyPH+OOPmmrZ/tnNhz8SpQUJMLaRFpsgwPyBZC2jYBSMglEwIgAAbuc3/dvx67gAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-9188-7425","institution":"Athens University of Economics and Business","correspondingAuthor":true,"prefix":"","firstName":"John","middleName":"","lastName":"Pavlopoulos","suffix":""},{"id":273070701,"identity":"5784087a-3d4b-4b27-a2c2-1d39a2b144c1","order_by":1,"name":"Panos Louridas","email":"","orcid":"","institution":"Athens University of Economics and Business","correspondingAuthor":false,"prefix":"","firstName":"Panos","middleName":"","lastName":"Louridas","suffix":""},{"id":273070702,"identity":"7e274cbf-8677-45d2-baad-77a79e7041ac","order_by":2,"name":"Panagiotis Filos","email":"","orcid":"","institution":"University of Ioannina","correspondingAuthor":false,"prefix":"","firstName":"Panagiotis","middleName":"","lastName":"Filos","suffix":""}],"badges":[],"createdAt":"2023-09-16 05:07:03","currentVersionCode":4,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-3360387/v4","doiUrl":"https://doi.org/10.21203/rs.3.rs-3360387/v4","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65937458,"identity":"338bd01a-eef2-44fc-9295-54b90313ec1c","added_by":"auto","created_at":"2024-10-04 15:15:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":414262,"visible":true,"origin":"","legend":"","description":"","filename":"GreekProverbAtlasEMNLP2024cameraready.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3360387/v4_covered_5697b287-fde7-4916-8bac-36b36a1294ba.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Towards a Greek Proverb Atlas: A Computational Spatial Exploration and Attribution of Greek Proverbs","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Athens University of Economics and Business","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"natural language processing, proverbs, spatial exploration, text geocoding, geographical attribution","lastPublishedDoi":"10.21203/rs.3.rs-3360387/v4","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3360387/v4","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eProverbs carry wisdom transferred orally fromgeneration to generation. Based on the placethey were recorded, this study introducesa \u003cem\u003epublicly-available\u003c/em\u003e and machine-actionabledataset of more than one hundred thousandGreek proverb variants. By quantifying thespatial distribution of proverbs, we show thatthe most widespread proverbs come from themainland while the least widespread proverbscome primarily from the islands. By focusingon the least dispersed proverbs, we present themost frequent tokens per location and under-take a benchmark in geographical attribution,using text classification and regression (textgeocoding). Our results show that this is a chal-lenging task for which specific locations can beattributed more successfully compared to oth-ers. The potential of our resource and bench-mark is showcased by two novel applications.First, we extracted terms moving the regressionprediction toward the four cardinal directions.Second, we leveraged conformal prediction toattribute 3,676 unregistered proverbs with sta-tistically rigorous predictions of locations eachof these proverbs was possibly registered in.\u003c/p\u003e","manuscriptTitle":"Towards a Greek Proverb Atlas: A Computational Spatial Exploration and Attribution of Greek Proverbs","msid":"","msnumber":"","nonDraftVersions":[{"code":4,"date":"2024-10-04 15:07:45","doi":"10.21203/rs.3.rs-3360387/v4","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":3,"date":"2024-02-15 17:29:29","doi":"10.21203/rs.3.rs-3360387/v3","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":2,"date":"2024-01-03 18:29:56","doi":"10.21203/rs.3.rs-3360387/v2","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2023-09-21 02:40:00","doi":"10.21203/rs.3.rs-3360387/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b2cfa8e8-dac9-43cf-b568-49dba01c20c4","owner":[],"postedDate":"October 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":28787053,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2023-09-21T02:40:01+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-04 15:07:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v4","identity":"rs-3360387","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3360387","identity":"rs-3360387","version":["v4"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}